scholarly journals Utilizing Text Mining, Data Linkage and Deep Learning in Police and Health Records to Predict Future Offenses in Family and Domestic Violence

2021 ◽  
Vol 3 ◽  
Author(s):  
George Karystianis ◽  
Rina Carines Cabral ◽  
Soyeon Caren Han ◽  
Josiah Poon ◽  
Tony Butler
Keyword(s):  
Mental Health ◽  
Domestic Violence ◽  
Deep Learning ◽  
Text Mining ◽  
Binary Classification ◽  
Contextual Information ◽  
Fine Tuning ◽  
Hands On ◽  
Mental Trauma ◽  
Transformer Model

Family and Domestic violence (FDV) is a global problem with significant social, economic, and health consequences for victims including increased health care costs, mental trauma, and social stigmatization. In Australia, the estimated annual cost of FDV is $22 billion, with one woman being murdered by a current or former partner every week. Despite this, tools that can predict future FDV based on the features of the person of interest (POI) and victim are lacking. The New South Wales Police Force attends thousands of FDV events each year and records details as fixed fields (e.g., demographic information for individuals involved in the event) and as text narratives which describe abuse types, victim injuries, threats, including the mental health status for POIs and victims. This information within the narratives is mostly untapped for research and reporting purposes. After applying a text mining methodology to extract information from 492,393 FDV event narratives (abuse types, victim injuries, mental illness mentions), we linked these characteristics with the respective fixed fields and with actual mental health diagnoses obtained from the NSW Ministry of Health for the same cohort to form a comprehensive FDV dataset. These data were input into five deep learning models (MLP, LSTM, Bi-LSTM, Bi-GRU, BERT) to predict three FDV offense types (“hands-on,” “hands-off,” “Apprehended Domestic Violence Order (ADVO) breach”). The transformer model with BERT embeddings returned the best performance (69.00% accuracy; 66.76% ROC) for “ADVO breach” in a multilabel classification setup while the binary classification setup generated similar results. “Hands-off” offenses proved the hardest offense type to predict (60.72% accuracy; 57.86% ROC using BERT) but showed potential to improve with fine-tuning of binary classification setups. “Hands-on” offenses benefitted least from the contextual information gained through BERT embeddings in which MLP with categorical embeddings outperformed it in three out of four metrics (65.95% accuracy; 78.03% F1-score; 70.00% precision). The encouraging results indicate that future FDV offenses can be predicted using deep learning on a large corpus of police and health data. Incorporating additional data sources will likely increase the performance which can assist those working on FDV and law enforcement to improve outcomes and better manage FDV events.

scholarly journals Automatic Extraction of Mental Health Disorders From Domestic Violence Police Narratives: Text Mining Study (Preprint)

2018 ◽  
Author(s):  
George Karystianis ◽  
Armita Adily ◽  
Peter Schofield ◽  
Lee Knight ◽  
Clara Galdon ◽  
...  
Keyword(s):  
Mental Health ◽  
Domestic Violence ◽  
Text Mining ◽  
Large Scale ◽  
New South ◽  
New South Wales ◽  
Mental Health Disorders ◽  
Free Text ◽  
South Wales ◽  
Health Disorders

BACKGROUND Vast numbers of domestic violence (DV) incidents are attended by the New South Wales Police Force each year in New South Wales and recorded as both structured quantitative data and unstructured free text in the WebCOPS (Web-based interface for the Computerised Operational Policing System) database regarding the details of the incident, the victim, and person of interest (POI). Although the structured data are used for reporting purposes, the free text remains untapped for DV reporting and surveillance purposes. OBJECTIVE In this paper, we explore whether text mining can automatically identify mental health disorders from this unstructured text. METHODS We used a training set of 200 DV recorded events to design a knowledge-driven approach based on lexical patterns in text suggesting mental health disorders for POIs and victims. RESULTS The precision returned from an evaluation set of 100 DV events was 97.5% and 87.1% for mental health disorders related to POIs and victims, respectively. After applying our approach to a large-scale corpus of almost a half million DV events, we identified 77,995 events (15.83%) that mentioned mental health disorders, with 76.96% (60,032/77,995) of those linked to POIs versus 16.47% (12,852/77,995) for the victims and 6.55% (5111/77,995) for both. Depression was the most common mental health disorder mentioned in both victims (22.30%, 3258) and POIs (18.73%, 8918), followed by alcohol abuse for POIs (12.24%, 5829) and various anxiety disorders (eg, panic disorder, generalized anxiety disorder) for victims (11.43%, 1671). CONCLUSIONS The results suggest that text mining can automatically extract targeted information from police-recorded DV events to support further public health research into the nexus between mental health disorders and DV.

scholarly journals Correction: Automatic Extraction of Mental Health Disorders From Domestic Violence Police Narratives: Text Mining Study

10.2196/13007 ◽  
2019 ◽  
Vol 21 (4) ◽  
pp. e13007 ◽  
Author(s):  
George Karystianis ◽  
Armita Adily ◽  
Peter Schofield ◽  
Lee Knight ◽  
Clara Galdon ◽  
...  
Keyword(s):  
Mental Health ◽  
Domestic Violence ◽  
Text Mining ◽  
Mental Health Disorders ◽  
Automatic Extraction ◽  
Health Disorders

scholarly journals Deep/Transfer Learning with Feature Space Ensemble Networks (FeatSpaceEnsNets) and Average Ensemble Networks (AvgEnsNets) for Change Detection Using DInSAR Sentinel-1 and Optical Sentinel-2 Satellite Data Fusion

2021 ◽  
Vol 13 (21) ◽  
pp. 4394
Author(s):  
Zainoolabadien Karim ◽  
Terence L. van Zyl
Keyword(s):  
Deep Learning ◽  
Change Detection ◽  
Transfer Learning ◽  
Binary Classification ◽  
Feature Space ◽  
Fine Tuning ◽  
Urban Change ◽  
Random Initialization ◽  
Optical Imagery ◽  
Sentinel 2

Differential interferometric synthetic aperture radar (DInSAR), coherence, phase, and displacement are derived from processing SAR images to monitor geological phenomena and urban change. Previously, Sentinel-1 SAR data combined with Sentinel-2 optical imagery has improved classification accuracy in various domains. However, the fusing of Sentinel-1 DInSAR processed imagery with Sentinel-2 optical imagery has not been thoroughly investigated. Thus, we explored this fusion in urban change detection by creating a verified balanced binary classification dataset comprising 1440 blobs. Machine learning models using feature descriptors and non-deep learning classifiers, including a two-layer convolutional neural network (ConvNet2), were used as baselines. Transfer learning by feature extraction (TLFE) using various pre-trained models, deep learning from random initialization, and transfer learning by fine-tuning (TLFT) were all evaluated. We introduce a feature space ensemble family (FeatSpaceEnsNet), an average ensemble family (AvgEnsNet), and a hybrid ensemble family (HybridEnsNet) of TLFE neural networks. The FeatSpaceEnsNets combine TLFE features directly in the feature space using logistic regression. AvgEnsNets combine TLFEs at the decision level by aggregation. HybridEnsNets are a combination of FeatSpaceEnsNets and AvgEnsNets. Several FeatSpaceEnsNets, AvgEnsNets, and HybridEnsNets, comprising a heterogeneous mixture of different depth and architecture models, are defined and evaluated. We show that, in general, TLFE outperforms both TLFT and classic deep learning for the small dataset used and that larger ensembles of TLFE models do not always improve accuracy. The best performing ensemble is an AvgEnsNet (84.862%) comprised of a ResNet50, ResNeXt50, and EfficientNet B4. This was matched by a similarly composed FeatSpaceEnsNet with an F1 score of 0.001 and variance of 0.266 less. The best performing HybridEnsNet had an accuracy of 84.775%. All of the ensembles evaluated outperform the best performing single model, ResNet50 with TLFE (83.751%), except for AvgEnsNet 3, AvgEnsNet 6, and FeatSpaceEnsNet 5. Five of the seven similarly composed FeatSpaceEnsNets outperform the corresponding AvgEnsNet.

scholarly journals Automatic Extraction of Mental Health Disorders From Domestic Violence Police Narratives: Text Mining Study

10.2196/11548 ◽  
2018 ◽  
Vol 20 (9) ◽  
pp. e11548 ◽  
Author(s):  
George Karystianis ◽  
Armita Adily ◽  
Peter Schofield ◽  
Lee Knight ◽  
Clara Galdon ◽  
...  
Keyword(s):  
Mental Health ◽  
Domestic Violence ◽  
Text Mining ◽  
Mental Health Disorders ◽  
Automatic Extraction ◽  
Health Disorders

scholarly journals Screening of Diabetes and Hypertension Based on Retinal Fundus Photographs Using Deep Learning

2019 ◽  
Author(s):  
Guangzheng Dai ◽  
Chenguang Zhang ◽  
Wei He
Keyword(s):  
Deep Learning ◽  
Binary Classification ◽  
Diabetic Control ◽  
Fine Tuning ◽  
Classification Model ◽  
Develop Model ◽  
Test Model ◽  
Fundus Photographs ◽  
Retinal Fundus ◽  
Retinal Photographs

ABSTRACTPurposeThe aim of this study was to use deep learning to screen for hypertension and diabetes based on retinal fundus images.MethodsWe collected 1160 retinal photographs which included 580 from patients with a diagnosis of hypertension or diabetes and 580 from normotensive and non-diabetic control. We divided this image dataset into (i) a development dataset to develop model and (ii) test dataset which were not present during the training process to assess model’s performance. A binary classification model was trained by fine-tuning the classifier and the last convolution layer of deep residual network. Precision, recall, the area under the ROC (AUC), and the area under the Precision-Recall curve (AUPR) were used to evaluate the performance of the learned model.ResultsWhen we used 3-channel color retinal photographs to train and test model, its prediction precision for diabetes or hypertension was 65.3%, the recall was 82.5%, the AUC was 0.745, and the AUPR was 0.742. When we used grayscale retinal photographs to train and test model, its prediction precision was 70.0%, the recall was 87.5%, the AUC was 0.803, and the AUPR was 0.779.ConclusionsOur study shows that trained deep learning model based on the retinal fundus photographs alone can be used to screen for diabetes and hypertension, although its current performance was not ideal.

scholarly journals Konseling Traumatik Untuk Menangani Gangguan Kesehatan Mental Trauma Pada Korban Pelecehan Seksual

2021 ◽  
Vol 5 (1) ◽  
pp. 29-41
Author(s):  
Ning Sasi Awaliyah ◽  
Ulin Nihayah ◽  
Khozaainatul Muna
Keyword(s):  
Mental Health ◽  
Domestic Violence ◽  
Child Abuse ◽  
Sexual Harassment ◽  
Large Impact ◽  
Literature Research ◽  
Mental Trauma ◽  
And Behavior

A person's mental health is affected by events in life that leave a large impact on a person's personality and behavior. These events can include domestic violence, child abuse, or long-term stress. The literature research combines the literature studies found by the authors. The results showed; 1) The victim is very traumatized by the sexual harassment incident and must be accompanied by a counselor to relax her mind. 2) implications of handling the victim, with several conditions experienced by the victim after treatment, including; a) feel relieved and already want to talk to other people and family b). feel have the spirit of life c). his condition is more stable because he feels comfortable after receiving therapy from the counselor

scholarly journals Advancing Stress Detection Methodology with Deep Learning Techniques Targeting UX Evaluation in AAL Scenarios: Applying Embeddings for Categorical Variables

Electronics ◽  
2021 ◽  
Vol 10 (13) ◽  
pp. 1550
Author(s):  
Alexandros Liapis ◽  
Evanthia Faliagka ◽  
Christos P. Antonopoulos ◽  
Georgios Keramidas ◽  
Nikolaos Voros
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
User Experience ◽  
Electrodermal Activity ◽  
Binary Classification ◽  
Research Question ◽  
Classification Problem ◽  
Categorical Variables ◽  
Stress Detection ◽  
Software Failures

Physiological measurements have been widely used by researchers and practitioners in order to address the stress detection challenge. So far, various datasets for stress detection have been recorded and are available to the research community for testing and benchmarking. The majority of the stress-related available datasets have been recorded while users were exposed to intense stressors, such as songs, movie clips, major hardware/software failures, image datasets, and gaming scenarios. However, it remains an open research question if such datasets can be used for creating models that will effectively detect stress in different contexts. This paper investigates the performance of the publicly available physiological dataset named WESAD (wearable stress and affect detection) in the context of user experience (UX) evaluation. More specifically, electrodermal activity (EDA) and skin temperature (ST) signals from WESAD were used in order to train three traditional machine learning classifiers and a simple feed forward deep learning artificial neural network combining continues variables and entity embeddings. Regarding the binary classification problem (stress vs. no stress), high accuracy (up to 97.4%), for both training approaches (deep-learning, machine learning), was achieved. Regarding the stress detection effectiveness of the created models in another context, such as user experience (UX) evaluation, the results were quite impressive. More specifically, the deep-learning model achieved a rather high agreement when a user-annotated dataset was used for validation.

scholarly journals Detection of Domestic Violence and Abuse by Community Mental Health Teams Using the BRAVE Intervention: A Multicenter, Cluster Randomized Controlled Trial

2021 ◽  
pp. 088626052110041
Author(s):  
Roos Ruijne ◽  
Cornelis Mulder ◽  
Milan Zarchev ◽  
Kylee Trevillion ◽  
Roel van Est ◽  
...  
Keyword(s):  
Mental Health ◽  
Domestic Violence ◽  
Randomized Controlled Trial ◽  
Controlled Trial ◽  
Referral Rates ◽  
Randomized Controlled ◽  
Cluster Randomized ◽  
And Control ◽  
Domestic Violence And Abuse

Despite increased prevalence of domestic violence and abuse (DVA), victimization through DVA often remains undetected in mental health care. To estimate the effectiveness of a system provider level training intervention by comparing the detection and referral rates of DVA of intervention community mental health (CMH) teams with rates in control CMH teams. We also aimed to determine whether improvements in knowledge, skills and attitudes to DVA were greater in clinicians working in intervention CMH teams than those working in control teams. We conducted a cluster randomized controlled trial in two urban areas of the Netherlands. Detection and referral rates were assessed at baseline and at 6 and 12 months after the start of the intervention. DVA knowledge, skills and attitudes were assessed using a survey at baseline and at 6 and 12 months after start of the intervention. Electronic patient files were used to identify detected and referred cases of DVA. Outcomes were compared between the intervention and control teams using a generalized linear mixed model. During the 12-month follow-up, detection and referral rates did not differ between the intervention and control teams. However, improvements in knowledge, skills and attitude during that follow-up period were greater in intervention teams than in control teams: β 3.21 (95% CI 1.18-4.60). Our trial showed that a training program on DVA knowledge and skills in CMH teams can increase knowledge and attitude towards DVA. However, our intervention does not appear to increase the detection or referral rates of DVA in patients with a severe mental illness. A low detection rate of DVA remains a major problem. Interventions with more obligatory elements and a focus on improving communication between CMH teams and DVA services are recommended.

Sign in / Sign up

Export Citation Format

Share Document